← Back to community benchmarks
Ornith-1.0-35B
Performance
16k
tokens
2,606
PP tok/s
58.1
TG tok/s
6287
TTFT (ms)
67.8
Peak mem (GB)
Hardware
Chip
M3 Ultra (80c)
Memory
512 GB
GPU Cores
80
Software
oMLX
v0.5.1
macOS
macOS 26.3
Context
16,384
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,983 | 63.4 | 65.6 GB | view |
| 4k | 2,850 | 62.7 | 66.4 GB | view |
| 8k | 2,845 | 61.8 | 67.0 GB | view |
| 16k | 2,606 | 58.1 | 67.8 GB | current |
| 32k | 2,206 | 56.2 | 69.6 GB | view |
| 64k | 1,638 | 50.9 | 72.3 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 63.4 | 1.00× |
| 2× | 72.9 | 1.15× |
| 4× | 128.2 | 2.02× |
| 8× | 77.2 | 1.22× |